Instructions to use Josephgflowers/Qllama-.5B-RAG-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Josephgflowers/Qllama-.5B-RAG-1 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Josephgflowers/Qllama-.5B-RAG-1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Josephgflowers/Qllama-.5B-RAG-1")
model = AutoModelForCausalLM.from_pretrained("Josephgflowers/Qllama-.5B-RAG-1", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Josephgflowers/Qllama-.5B-RAG-1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Josephgflowers/Qllama-.5B-RAG-1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Josephgflowers/Qllama-.5B-RAG-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Josephgflowers/Qllama-.5B-RAG-1

SGLang

How to use Josephgflowers/Qllama-.5B-RAG-1 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Josephgflowers/Qllama-.5B-RAG-1" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Josephgflowers/Qllama-.5B-RAG-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Josephgflowers/Qllama-.5B-RAG-1" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Josephgflowers/Qllama-.5B-RAG-1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Josephgflowers/Qllama-.5B-RAG-1 with Docker Model Runner:
```
docker model run hf.co/Josephgflowers/Qllama-.5B-RAG-1
```

This model needs further fine tuning.

See: txtai-rag.py for rag implimentation with txt ai wikipedia.

Llamafyd version of Qwen .5B further fine tuned 1 epoch on wiki, math, science, and chat datasets. Based on Cinder data. This model further fine tuned 1 epoch on rag data.

Rough list of final datasets: formatted_beaugogh-openorca-multiplechoice-10k.txt formatted_BYC-Sophie-samsum-chatgpt-summary.txt formatted_conversation_bio.txt formatted_conversation_create_cinder_1.txt formatted_conversation_Electrical-engineering.txt formatted_conversation_multiturn_stem.txt formatted_conversation_physics.txt formatted_conversation_qa_rag_chem_prog_dataset.txt formatted_conversation_qa_robot_ai_dataset.txt formatted_conversation_qa_shopify_dataset1_rag.txt formatted_conversation_qa_shopify_dataset_rag.txt formatted_dyumat-databricks-dolly-5k-rag-split.txt formatted_Hypoxiic-wikipedia-summary-subset1k-summary_token.txt formatted_neural-bridge-rag-dataset-12000.txt formatted_rachid16-rag_finetuning_data.txt formatted_tiny_stories_1_summary_token_tag_token-xaa.txt formatted_tiny_stories_2_summary_token_assistant-xah.txt med_rag_small.txt z_formatted_cinder_test.txt

Downloads last month: 10

Safetensors

Model size

0.5B params

Tensor type

F16